W1siziisijiwmjavmduvmdqvmtavmjivmjevmziwl3dlymluyxigagvhzgvylmpwzyjdlfsiccisinrodw1iiiwimtawmhg5mdbcdtawm2mixv0

I AM A

JOBSEEKER.

continue to candidate homepage

W1siziisijiwmtkvmdkvmjcvmtmvntkvndmvnju3l1jnmv8ynzg5ifttbwfsbf0uanbnil0swyjwiiwidgh1bwiilcixmdawedkwmfx1mdazyyjdxq

I AM

HIRING.

Continue to client homepage

NLP Research Scientist

  • Location

    New York, USA

  • Sector:

    Data Science

  • Job type:

    Permanent

  • Salary:

    US$150000.00 - US$160000.00 per annum + 20% bonus + 75K LTP

  • Contact:

    Lewis Adams-Dunstan

  • Email:

    Lewis.ad@darwinrecruitment.com

  • Job ref:

    JN -052021-88436_1620680690

  • Published:

    about 1 month ago

  • Startdate:

    ASAP

Do you have experience applying NLP to the pharmaceutical space?

Are you proficient in Python with experience in understanding existing complex code?

Have you developed machine learning models at scale from inception to business impact?

My client, an NYC based drug discovery firm located in NYC is looking for an NLP Scientist with experience in Natural Language Understanding applied to information extraction to join their team an as Associate Director - NLP Scientist.

You're main responsibility in this role will be to build and optimize the unstructured data ingestion pipeline that underlies their pharmaceutical analysis engine.

Here's a deeper insight into what you'll be doing day to day…

Information extraction and linkage:

- Implement/improve state-of-the-art Named Entity Recognition for multiple entities leveraging multi-task learning

- Establish relationship extraction between entities with classification of relationship types

- Perform topic modeling and documents classification

- Implement/improve state-of-the-art Named Entity Normalization to link entities to the right entry in our Knowledge Graph

- Leverage graph algorithms for insight extraction and to enhance NLP

- Support the deployment of our NLP models into our production ETL

Insight extraction:

- Leverage the information extracted from documents to design algorithms to alert analysts of important catalyst events

- Apply a combination of NLP models to perform analysis for the various stakeholders (drug discovery, competitive intelligence, etc…)

To be considered you must have:

- Master's degree plus 5+ years' work experience (PhD plus 2+ years' experience preferred)

- Experience working in the pharmaceutical industry or bio-engineering is essential

- Experience working in Linux environment and using GitHub

- Experience reproducing published results and improving on them (using either TensorFlow 2, Keras or PyTorch)

- Experience working with NLP frameworks (e.g., NLTK, spaCy) and pre-trained models (e.g., BERT) is a plus

- Mathematical and statistical understanding of mainstream NLP and machine learning techniques (e.g., TF-IDF, CRFs, similarity measure)

- Successful experience in collaborating on code development

- Experience in graph database (RDF triple store), SPARQL query language and knowledge graph algorithms is a plus

- Familiarity with cloud-hosted distributed computing (AWS EC2)

- Familiarity with knowledge graph inference and interfacing with Neural Network is a plus

Darwin Recruitment is acting as an Employment Agency in relation to this vacancy.

Save job